Monthly Stream Flow Prediction Using Support Vector Machine Based on Principal Component Analysis
Roohollah Noori,
Amir Khakpour,
Majid Dehghani,
Ashkan Farokhnia
Affiliations
Roohollah Noori
Member of Water Research Institute, Ministry of Energy, Ph.D Student of Environmental Eng., Graduate Faculty of Environment, University of Tehran
Amir Khakpour
Management Director of CELCO , and Ph.D Student of Environmental Eng., Graduate Faculty of Environment, University of Tehran
Majid Dehghani
Ph.D Student of Hydraulic Eng., Dept. of Eng., Islamic Azad University, Science and Research Branch, Tehran
Ashkan Farokhnia
Member of Water Research Institute, Ministry of Energy, Ph.D. Student of Hydraulic Structure, College of Agriculture, Tarbiyat Modarres University, Tehran
The main goal of this research is to evaluate the role of input selection by Principal Component Analysis (PCA) on Support Vector Machine (SVM) performance for monthly stream flow prediction. For this purpose, SVM is used to predict monthly flow as a function of 18 input variables. PCA is subsequently employed to reduce the number of input variables from 18 to 5 PCs which are finally fed into the SVM model. SVM and PCA-SVM models are evaluated in terms of their performance using a developed statistic by the authors. Findings show that preprocessing of input variables by PCA improved SVM performance.
